A new artificial intelligence weather forecasting model developed by researchers has demonstrated superior accuracy compared to conventional physics-based systems in global medium-range weather predictions. The AI model, trained on decades of historical weather data, can generate 10-day forecasts in minutes on a single computer, a task that typically requires hours on supercomputers using traditional methods. In head-to-head comparisons, the AI system more accurately predicted key atmospheric variables, including temperature and wind patterns, across multiple regions. While promising, experts note that further testing is needed for extreme weather events and long-term reliability. The development signals a potential shift in meteorological science toward hybrid AI-physics approaches. Read the full article at https://sciencedaily.com/releases/2024/07/240711215443.htm.